Anthropic
Claude Opus 4.6 (Non-reasoning, High Effort)
Opus 4.6 is the world’s best model for coding and professional work, built to power agents that take on whole categories of real-world work. It excels across the entire SDLC, breaking through on hard problems, identifying complex bugs, and demonstrating deeper codebase understanding. It also delivers a step-change in knowledge work, with near-production-ready documents, presentations, and spreadsheets on the first pass.
Introducing Claude OpusModel Snapshot
TypeLanguage
ReleaseFeb 5, 2026
Context1,000,000
Tagstool-use, reasoning, vision, file-input
Overall
Rank #34 across 526
46.5
Coding
Rank #19 across 436
47.6
Blended Price
Rank #337 across 357
$10.94/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed40.9 tok/s
First Token1.43s
Max Output128,000
Pricing
Blended$10.94/M
Input$6.25/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 46.5 | #34 |
| Artificial Analysis Coding Index | coding | 47.6 | #19 |
| GPQA | reasoning | 84.0% | #77 |
| Humanity's Last Exam | reasoning | 18.6% | #88 |
| SciCode |